Unsupervised Part-of-Speech Acquisition for Resource-Scarce Languages.
Sajib DasguptaVincent NgPublished in: EMNLP-CoNLL (2007)
Keyphrases
- pos taggers
- part of speech
- pos tagging
- n gram
- natural language processing
- syntactic categories
- unsupervised grammar induction
- word sense disambiguation
- chinese word segmentation
- grammar induction
- penn treebank
- training corpus
- target language
- language independent
- text documents
- multiword
- word segmentation
- tf idf
- named entity recognition
- machine translation
- search engine
- machine learning
- data mining
- domain adaptation
- semantic similarity
- wordnet
- expert systems